mirror of
https://github.com/jart/cosmopolitan.git
synced 2025-07-06 11:18:30 +00:00
Introduce prompt caching so prompts load instantly
This change also introduces an ephemeral status line in non-verbose mode to display a load percentage status when slow operations are happening.
This commit is contained in:
parent
bf6459e324
commit
b31ba86ace
7 changed files with 333 additions and 103 deletions
4
third_party/ggml/common.cc
vendored
4
third_party/ggml/common.cc
vendored
|
@ -1,5 +1,5 @@
|
|||
/*-*- mode:c;indent-tabs-mode:nil;c-basic-offset:4;tab-width:8;coding:utf-8 -*-│
|
||||
│vi: set net ft=c ts=4 sts=4 sw=4 fenc=utf-8 :vi│
|
||||
/*-*-mode:c++;indent-tabs-mode:nil;c-basic-offset:4;tab-width:8;coding:utf-8-*-│
|
||||
│vi: set net ft=c++ ts=4 sts=4 sw=4 fenc=utf-8 :vi│
|
||||
╚──────────────────────────────────────────────────────────────────────────────╝
|
||||
│ │
|
||||
│ llama.cpp │
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue